Skip to content
MCP server

simpletel

Query OpenTelemetry traces and account usage from simpletel with a coding agent

Runs locallyStatus and history
Install
Pricing
Freemium
Platforms
CLI, API
Runs
Locally
Version
20261109.1604.14-d016369
Listing updated
3 days ago

About simpletel

simpletel is a freemium MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Debugging a failing request usually means leaving the editor for a dashboard. This server is built into the simpletel command line tool and gives an agent the same read commands over stdio, so it can pull a failing trace and reason about its spans without any screenshots.

It advertises four tools. Three are team-scoped: listing traces newest first with filters for time window, service, errors only and minimum duration; fetching one trace in full with span events and correlated logs; and a verify check that polls until a service has a fresh trace with spans from library instrumentation, used to confirm onboarding worked. A fourth shows the account's plan, month-to-date records, allowance and spend cap and needs a logged-in user token.

It ships as a single static binary with no runtime, and also as a container image. The backend it talks to is simpletel, an OpenTelemetry store on one SQLite file that accepts traces, logs and metrics over standard OTLP. Pricing is metered per record (a span, log record or metric point), with hard caps rather than overage surprises.

Install

Run in a terminal

claude mcp add simpletel -- docker run -i --rm ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369

Add to claude_desktop_config.json

{
  "mcpServers": {
    "simpletel": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "simpletel": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "simpletel": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "simpletel": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "simpletel": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369"
      ]
    }
  }
}

Tools this server provides (4)

Taken from the project documentation; the running server may differ.

get_traces
Lists the team's traces newest first with filters for since, service, errors_only, min_duration and limit.
get_trace
Fetches one trace in full with spans, span events and correlated logs.
verify
Polls until a service has a fresh trace with library-instrumented spans.
usage
Shows plan, month-to-date records, allowance and spend cap.

What it does

Trace listing
Lists traces newest first, filtered by time, service, errors only or minimum duration.
Full trace fetch
Returns every span, span event and correlated log record for one trace id.
Onboarding verify
Polls until a service shows a fresh trace carrying library-instrumented spans.
Usage report
Shows plan, month-to-date records, allowance and spend cap for the account.
Single binary
Built into the simpletel CLI with no runtime or background service.
Container option
Also published as an OCI image on ghcr.io.

Good for

  • Ask an agent why a request just failed in production
  • Find slow requests above a duration threshold
  • Confirm a new service is exporting traces correctly
  • Check how much of the monthly record allowance is used

Pricing

Freemium, from $19 a month

Free: 2M records/month, 7-day retention; Starter $19/mo; Team $79/mo; Scale from $499/mo

Prices change. Check simpletel.dev before you buy.

simpletel FAQ

What counts as a record for billing?

One span, one log record or one metric data point, not gigabytes.

What plans exist?

Free ($0, 2M records a month, 7 days retention), Starter ($19/mo), Team ($79/mo) and Scale from $499/mo.

What happens at the cap?

Ingest stops: at the allowance on the free tier, and at 2x the allowance on paid plans by default.

Is it scoped to a team?

get_traces, get_trace and verify are team-scoped; usage is account-scoped.

Is there a seat charge?

No. The pricing page says there are no seats.

Is simpletel free?

simpletel has a free plan, with paid plans for more usage or features. Paid plans start at $19 a month.

How do I add simpletel to Claude Code?

Run this command in your terminal: claude mcp add simpletel -- docker run -i --rm ghcr.io/willnewby/simpletel-mcp:20261109.1604.14-d016369

What are the best alternatives to simpletel?

The closest alternatives to simpletel are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to simpletel

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data